Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/hiramgabriel1/nightdev_rep/agents-mdgit clone --depth 1 https://github.com/hiramgabriel1/nightdev_repWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/hiramgabriel1/nightdev_rep/agents-md)<a href="https://agentmods.dev/instructions/hiramgabriel1/nightdev_rep/agents-md"><img src="https://agentmods.dev/badge/instructions/hiramgabriel1/nightdev_rep/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00357 | $0.00357 |
| Opus 5 | $0.00179 | $0.00179 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
nightdev_rep AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
AGENTS.md
Commands
pnpm dev— start bot withtsx watch(auto-reload)pnpm build— TypeScript compile todist/pnpm start— run compiled output- No lint or test scripts configured yet
Architecture
- Single-process Telegram bot, entrypoint:
src/index.ts src/commands.ts—/start,/helphandlerssrc/handlers.ts— text message matchingsrc/logger.ts— typed logger class withLogLevelenum
Key conventions
- Uses
dotenv—src/index.tsimports'dotenv/config'at top TELEGRAM_BOT_TOKENrequired in.env(see.env.example)node-telegram-bot-apiv1.1.0 uses ESM named exports, not namespace types- TypeScript:
module: "Node16",moduleResolution: "node16",allowSyntheticDefaultImports: true - Import paths must include
.jsextension (ESNext module resolution)
Git workflow
- Always commit changes after completing a task (do not wait for user to ask)
- Use Conventional Commits format:
type(scope): description- Types:
feat,fix,docs,refactor,chore,test,style,perf - Examples:
feat: add message logger,fix: resolve token loading order
- Types:
- Stage only files related to the change (
git add <files>) - Run
pnpm buildbefore committing to verify compilation - Always
git pushafter committing
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 34 lines · 357 tokens per session scan A ea4503726c1f
nightdev_rep AGENTS.md is an instructions file published in the GitHub repository hiramgabriel1/nightdev_rep (11 stars, last pushed 1mo ago), licensed MIT. It adds 357 tokens to every session, about $0.0018 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
MagicAIBuilder AGENTS.md
AGENTS.md instructions for KaelSensei/MagicAIBuilder, covering magicaibuilder — coding standards, language & runtime, type safety — non-negotiable rules, no type assertions (as) and no non-null assertions (!).
claworc CLAUDE.md
Claude Code instructions for gluk-w/claworc, covering claworc, repository structure, architecture, configuration and terminology.
MagicAIBuilder CLAUDE.md
Claude Code instructions for KaelSensei/MagicAIBuilder, covering magicaibuilder — project instructions, skills — load these for the right job, project-specific rules (not covered by any skill), branch flow — dev → staging → main and documentation discipline.
ClawFleet CLAUDE.md
Instructions for clawfleet/ClawFleet, covering claude.md, project, architecture layers, clawsandbox (infrastructure) and clawfleet (product).
sea-notes-saas-starter-kit CLAUDE.md
Instructions for digitalocean/sea-notes-saas-starter-kit, covering claude memory file, project overview, technology stack, commands and database.
cargoshipper-mcp CLAUDE.md
Claude Code instructions for scarr7981/cargoshipper-mcp, covering cargoshipper mcp server, project overview, ⚠️ important safety warning, 🤖 vibecode friendly project and available mcp servers.